I am a Ph.D. candidate in computer science at Princeton University, advised by Karthik Narasimhan. Previously, I graduated from Yao Class at Tsinghua University.

My research interests include language, games, representation learning, cognitive science, and AI in general.

My personal interests include reading, basketball, travel, and rap.


  • Self-Attention Networks Can Process Bounded Hierarchical Languages. Shunyu Yao, Binghui Peng, Christos Papadimitriou, Karthik Narasimhan. ACL 2021. [pdf] [code]

  • Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents. Shunyu Yao, Karthik Narasimhan, Matthew Hausknecht. NAACL 2021. [pdf] [code] [project]

  • Keep CALM and Explore: Language Models for Action Generation in Text-based Games. Shunyu Yao, Rohan Rao, Matthew Hausknecht, Karthik Narasimhan. EMNLP 2020. [pdf] [code]

  • The Fine Structure of Surprise in Intuitive Physics: When, Why, and How Much?. Kevin Smith, Lingjie Mei, Shunyu Yao, Jiajun Wu, Elizabeth S. Spelke, Joshua B. Tenenbaum, Tomer D. Ullman. CogSci 2020. [pdf]

  • Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations. Kevin Smith*, Lingjie Mei*, Shunyu Yao*, Jiajun Wu, Elizabeth S. Spelke, Joshua B. Tenenbaum, Tomer D. Ullman. NeurIPS 2019. [pdf] [code] [data] [project] [MIT news]

  • 3D-aware Scene Manipulation via Inverse Graphics. Shunyu Yao*, Tzu-Ming Harry Hsu*, Jun-Yan Zhu, Jiajun Wu, Antonio Torralba, William T. Freeman, Joshua B. Tenenbaum. NeurIPS 2018. [pdf] [code] [project]